人体运动数据实时捕捉系统的设计与实现

采用电子测量方法进行人体运动数据实时捕捉,构建人体运动数据实时捕捉系统,系统包括硬件设计和软件设计两部分,采用HP E1433A高速数据捕获总线模块记录人体运动数据并存储到数据硬盘中。进行运动数据捕捉的发射机、接收机、控制器等硬件构件设计,软件设计通过PXI实时系统触发各通道实现数据同步采集和回放,进行数据可视化模块设计和数据触发设置。最后进行系统调试,结果表明,采用该数据捕捉系统能实时进行人体数据的记录和输出,系统的稳定性较好。     

Action recognition on motion capture data using a dynemes and forward differences representation

In this paper we introduce a novel method for action/movement recognition in motion capture data. The joints orientation angles and the forward differences of these angles in different temporal scales are used to represent a motion capture sequence. Initially K-means is applied on training data to discover the most representative patterns on orientation angles and their forward differences. A novel K-means variant that takes into account the periodic nature of angular data is applied on the former. Each frame is then assigned to one or more of these patterns and histograms that describe the frequency of occurrence of these patterns for each movement are constructed. Nearest neighbour and SVM classification are used for action recognition on the test data. The effectiveness and robustness of this method is shown through extensive experimental results on four standard databases of motion capture data and various experimental setups.     

Automatic selection of frequency and time intervals for classification of EEG signals

A novel technique is presented for the automatic selection of time and frequency intervals to be used in feature extraction on multidimensional signals acquired by an electroencephalogram (EEG). This technique is completely automatic, adaptive (task independent), and does not require any specific prior domain knowledge. Experimental results obtained by integrating the proposed technique in a system for brain computer interface (BCI) confirm its effectiveness.     

基于动作捕捉技术的畲族舞蹈动态造型的信息化分析

基于动作捕捉技术的畲族舞蹈动态造型的分析与研究,不同于通过传统DV拍摄方式的研究,它通过标记的搜索、舞者姿态数据获取、舞者姿态数据曲线形成、自遮挡的处理及数据修正等步骤精确记录真实舞者各关节的三维运动轨迹,实现动作的到点分析,有利于真实地保存每组畲族舞蹈的艺术精华,有利于为今后对畲族舞蹈的研究、创编和影视还原提供精准的数字平台,也为作为省非物质文化遗产的代表作名录的畲族舞蹈的保护开辟一个新的领域,对于民族文化的保护和科学化发展有着深远的意义。     

Probabilistic inference of multijoint movements, skeletal parameters and marker attachments from diverse motion capture data

This paper describes a comprehensive solution to the problem of reconstructing the multijoint movement trajectories of the human body from diverse motion capture data. The problem is formulated in a probabilistic framework so as to handle multiple and unavoidable sources of uncertainty: sensor noise, soft tissue deformation and marker slip, inaccurate marker placement and limb measurement, and missing data due to occlusions. All unknown quantities are treated as state variables even though some of them are constant. In this way, state estimation and system identification can be performed simultaneously, obtaining not only the most likely values but also the confidence intervals of the joint angles, skeletal parameters, and marker positions and orientations relative to the limb segments. The inference method is a Gauss-Newton generalization of the extended Kalman filter. It is adapted to the kinematic domain by expressing spatial rotations via quaternions and computing the sensor residuals and their Jacobians analytically. The ultimate goal of this project is to provide a reliable data analysis tool used in practice. The software implementation is available online.     

运动捕捉技术在影视动画制作中的应用研究

运动捕捉技术是影视动画制作中的新技术。在对运动捕捉技术分析的基础上，讨论了基于光学运动捕捉技术制作动画的原理和方法，并详细描述了标记点跟踪和三雏重建等技术在影视动画制作过程中的应用。     

Fault detection in configurable switched-capacitor filters using transient analysis and dynamic time warping

In this work, we address a low-cost test of switched capacitors filters embedded in configurable analog sections. The proposal improves the Transient Analysis Method (TRAM) by incorporating a similarity measure, dynamic time warping. In this way, we extend TRAM to cases that that initially were not compatible and simplify the test of filters of order higher than two. This paper performs the test evaluation by developing a new simulation model of the addressed system that supports fault injection and simulation. A comparison with experimental data in both normal and faulty behavior validates the model. We consider catastrophic faults in the switches (stuck at open and short) and capacitors (shorts and opens), and deviation faults in the capacitors. The fault simulation results validate the test proposed here.

     

Improved motion estimation time using a combination of dynamic reference frame selection and residue-based mode decision

Motion estimation using multiple reference frames is widely used as the basis for recent video coding standards (eg. H.264/AVC) to achieve increased coding efficiency. However, this increases the complexity of the encoding process. In this paper, a new technique for efficient motion estimation is proposed. A combination of multiple reference frame selection and image residue-based mode selection is used to improve motion estimation time. By dynamic selection of an initial reference frame in advance, the number of reference frames to be considered is reduced. In addition, from examination of the residue between the current block and reconstructed blocks in preceding frames, variable block size mode decisions are made. Modified initial motion vector estimation and early stop condition detection are also adopted to speed up the motion estimation procedure. Experimental results compare the performance of the proposed algorithm with a state of the art motion estimation algorithm and demonstrate significantly reduced motion estimation time while maintaining PSNR performance.     

Waveform selection in radar target classification

We apply a sequential experiment design procedure to the problem of signal selection for radar target classification. Radar waveforms are designed to discriminate between targets possessing a doubly spread reflectivity function that are observed in clutter. The waveforms minimize decision time by maximizing the discrimination information in the echo signal. Each waveform selected maximizes the Kullback-Leibler (1951) information number that measures the dissimilarity between the observed target and the alternative targets. We discuss in details two scenarios. In the first scenario, the target environment is assumed fixed during illumination. In this case, the optimal waveform selection strategy leads to a fixed library of waveforms. During actual classification, the sequence in which the waveforms are selected from the library is determined from the noise to clutter power in the range-Doppler support of the targets. In the second scenario, the target environment changes between pulse transmissions. In this case, the maximum discrimination information is obtained by a repeated transmission of a single waveform designed from the reflectivity function of the targets. We show that our choice of signals can produce significant gains in detection performance     

运动数据中的最优关联数据的分类分析

针对传统的分类方法在对运动数据的最优关联数据进行分类时,存在分类误差大、效率低的问题,提出基于决策树寻优的运动数据中的最优关联数据的分类算法。采用有向图模型构建运动数据的最优关联数据分布式结构模型,对采集的运动数据进行非线性时间序列特征重构,在重构的运动数据高维特征空间中进行运动数据的关联性映射,提取反映运动数据类别的属性特征,通过决策树寻优方法实现运动数据的自适应分类。仿真结果表明,采用该方法进行运动数据中的最优关联数据分类,其准确性较好、误分率较低,从而有效挖掘运动数据的关联信息,实现运动特征监测。     

运动数据中的最优关联数据的分类分析

针对传统关联数据分类方法一直存在分类精度差的问题,提出一种运动数据中的最优关联数据的分类方法。由于运动数据的变化量十分的庞大,同时变化程度也无法用规律进行推导,因此需要确定运动数据中的最优关联数据,通过最优关联数据的关联性进行高速提取,使用异导函数对提取的数据进行系统的分类。为了保证提出的运动数据中的最优关联数据的分类方法的有效性,设计对比仿真实验,通过实验数据表明,提出的运动数据中的最优关联数据的分类方法能够准确地对运动数据中的最优关联数据进行系统分类。     

Automatic selection of reference data for use in a nearest-neighbor method of pattern classification (Corresp.)

Two methods for automatic selection of nearest-neighbor reference data have been compared in small-scale experimentation. One of the methods is original and appears to be more successful than Hart's well-known "condensed nearest-neighbor" method [1].     

运动捕获技术在电力安全仿真培训中的应用

为了满足电力企业对员工业务能力的要求,文中提出了一种基于虚拟现实技术的光学运动捕获系统。通过电力模拟单元、ZigBee技术和OpenGL图形库建立电力设备模型、虚拟操作环境和人体模型。利用人体模型驱动算法和卡尔曼滤波算法解决了特征点缺失的问题。实验结果表明,实际运动捕获和实时动画显示的跟踪过程中,采用卡尔曼滤波算法提取特征点更为准确,3D坐标的平均绝对误差(MAD)的平均值为1. 61mm,平均相对误差(MRE)的平均值为2. 23%,该系统能够提高受训者的体验和沉浸感。     

Suppression of slice selection axis motion artifacts in MRI

Patient motion during data acquisition in magnetic resonance imaging causes artifacts in the reconstructed image, which for two-dimensional Fourier transform imaging techniques appear as blurring and ghost repetitions of the moving structures. T. Mitsa et al. (1990) proposed a technique for suppressing artifacts from periodic motion along the slice selection axis. A different approach to the same problem is presented which is not restricted to periodic motion. The algorithm is verified using a simulated phantom and motion. It is also shown to perform well in the presence of noise and motion within the imaging plane.     

网络大数据平台中的特征数据分类系统设计与实现

网络大数据平台中特征数据的有效分类,是提高网民查询体验、开发新型应用的有效途径。为此,设计稳定性好、资源占用率低的网络大数据平台特征数据分类系统。系统的显示端是网民的直接应用端,其主要进行网络大数据的获取、大数据获取结果的显示和特征分类结果的显示。服务端利用SOA体系结构为网络大数据平台提供特征数据的分类服务,其将特征数据的分类标准纳入到网络大数据中,并传递给逻辑层处理端。逻辑层处理端根据特征数据分类标准,利用云计算和策略设计对网络大数据集合进行特征提取,其特征提取算法于软件中给出。特征数据分类端根据逻辑层处理端所提取出的大数据特征,利用特征向量机进行特征数据的自动分类工作。实验结果表明,所设计的系统稳定性好、资源占用率低。     

Erasure, capture, and random power level selection inmultiple-access systems

Multiple-access algorithms that handle erasures as well as captures are introduced. The algorithms are evaluated according to the maximal throughput that they can support for a Poisson arrival process. An example is given which shows that, in practice, the positive effect of captures compensates the negative effect of erasures. An approach that effectively utilizes the capture phenomena is introduced. This approach incorporates a random power-level-selection scheme that allows each node to choose randomly to transmit in one of several allowable levels of power. Design issues such as number of levels, selection schemes, etc. are discussed     

人体运动数据实时捕捉系统的设计与实现

应用微机电技术设计人体运动数据实时捕捉系统。系统在人体的重点运动部位安装16个传感器收集人体运动数据,通过卡尔曼滤波给出人体运动数据实时状态估计值,使用微机电技术优化估计结果。按顺序对估计结果进行解算,将解算结果输入人体重要运动关节模型,实时进行三维虚拟显示。最后对系统的接线方式和捕捉指令进行实现。实验验证结果表明设计的系统综合捕捉效果强。     

Dynamic cooperator selection in cognitive radio networks

The primary objective of cooperation in cognitive radio (CR) networks is to increase the spectrum access efficiency and improve the network performance. However, Byzantine adversaries or unintentional erroneous conduct in cooperation can lead to destructive behavior of CR users that can decrease their own and others’ performances. This work presents a dynamic solution for cooperation reliability in conditions with constraints typical for a CR network. Specifically, in CR networks, the information on the success of cooperation can be limited only to cases with interference; when malicious, cooperators can be completely non-correlated and can alter behavior; and the set of available cooperators can dynamically change in time. In order to face these challenges, each CR user autonomously decides with whom to cooperate by learning cooperators behavior with a reinforcement learning (RL) algorithm. This RL algorithm determines the suitability of the available cooperators, and selects the most appropriate ones to cooperate with the objective to increase the efficiency of spectrum access in CR networks. The simulation results demonstrate the learning capabilities of the proposed solution and especially its reliable behavior under highly unreliable conditions.     

基于分类的运动矢量平滑和纠正方法

对于帧率上变换算法中运动矢量估计不准确的问题,文中提出了一种新的运动矢量处理算法,较好地纠正了错误的运动矢量。该算法根据前后向运动矢量的一致性程度,以及对应块的绝对差值和,对运动矢量进行了可靠性分类。针对分布在纹理相似区的错误运动矢量,利用时间和空间相关性联合纠正;对于物体边缘区域则分解为小块重搜索运动矢量,以避免边缘模糊现象。实验结果显示,算法可以较好地纠正运动矢量。